© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93259
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fully
    -0.07
     dot
    -0.06
    vey
    -0.06
    acet
    -0.06
    .cn
    -0.06
    azy
    -0.06
    ered
    -0.06
    Å¡k
    -0.06
    ông
    -0.06
    جة
    -0.06
    POSITIVE LOGITS
     jadx
    0.07
    chwitz
    0.07
    fragistics
    0.07
    inder
    0.07
    .getContentPane
    0.06
    )throws
    0.06
    elerik
    0.06
    ãĥ¼ãĥĵ
    0.06
    flater
    0.06
    mbH
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.